Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Google's Latest Machine Vision Breakthrough

Soulskill posted about a year ago | from the can-now-gauge-your-receptivity-to-ads-by-scanning-your-face dept.

AI 113

mikejuk writes "Google Research recently released details of a Machine Vision technique which might bring high power visual recognition to simple desktops and even mobile computers. It claims to be able to recognize 100,000 different types of object within a photo in a few minutes — and there isn't a deep neural network mentioned. It is another example of the direct 'engineering' approach to implementing AI catching up with the biologically inspired techniques. This particular advance is based on converting the usual mask-based filters to a simpler ordinal computation and using hashing to avoid having to do the computation most of the time. The result of the change to the basic algorithm is a speed-up of around 20,000 times, which is astounding. The method was tested on 100,000 object detectors using over a million filters on multiple resolution scalings of the target image, which were all computed in less than 20 seconds using nothing but a single, multi-core machine with 20GB of RAM."

cancel ×

113 comments

Sorry! There are no comments related to the filter you selected.

Porn Collection (5, Funny)

sycodon (149926) | about a year ago | (#44368041)

Can it sort and identify duplicates automagically in my porn collection?

Re:Porn Collection (0)

Anonymous Coward | about a year ago | (#44368151)

Can it sort and identify duplicates automagically in my porn collection?

Upload it to Google Drive

Re:Porn Collection (0)

Anonymous Coward | about a year ago | (#44368165)

FSLint works wonderfully for finding and sorting (by how often each is duplicated) such dupes.

http://www.pixelbeat.org/fslint/

Re:Porn Collection (1)

K. S. Kyosuke (729550) | about a year ago | (#44368489)

What, it uses machine vision to find out similar images and image sequences?

Re:Porn Collection (2)

cristiroma (606375) | about a year ago | (#44368545)

No, because it would go mad and overheat the CPU, looking through all that porn.

Re:Porn Collection (1)

FatLittleMonkey (1341387) | about a year ago | (#44368983)

"Pixelbeat"

Re:Porn Collection (1)

MBGMorden (803437) | about a year ago | (#44369635)

You may be joking, but when people are looking for "duplicate" videos a comparison of hashes isn't applicable. They're usually not bit-for-bit duplicates. Usually if I want to locate duplicate files I want to match up two files as duplicates that are the same input video, but one might be offset by a few seconds, they might be at different resolutions, and might be compressed using different codecs. To a machine using hash checks those two files are nothing alike, but to a human they're the same.

Though I doubt something on the level of the program mentioned on the article is needed, it would still be a nice type of utility to have.

Re:Porn Collection (5, Funny)

Impy the Impiuos Imp (442658) | about a year ago | (#44368263)

Can it sort and identify duplicates automagically in my porn collection?

Sure! It sorted your stuff into these categories:

400-lb. naked guys kissing
Stuff reported to the NSA
Someone's drawing of a dragon humping a car
Taylor Swift

Over 750,000 pictures in all!

Re:Porn Collection (1)

chris.alex.thomas (1718644) | about a year ago | (#44368483)

hahahahahahha, well done sir!

Re:Porn Collection (3, Funny)

K. S. Kyosuke (729550) | about a year ago | (#44368495)

Does it support boolean operators? So that, you know, you could find 400-lb. naked guys kissing Taylor Swift and similar material?

Re:Porn Collection (1)

OakDragon (885217) | about a year ago | (#44369659)

Does it support boolean operators? So that, you know, you could find 400-lb. naked guys kissing Taylor Swift and similar material?

Facebook "Graph Search" to the rescue!

Re:Porn Collection (0)

Anonymous Coward | about a year ago | (#44369191)

Just an update to the old fairy tale... Substitute "Grandmother" with the government.
As any fairy tale goes, there is a moral to this story.

"Grandmother, what big arms you have!" - nuclear arms
"All the better to hug you with, my dear."
"Grandmother, what big legs you have!"
"All the better to run with, my child." - all to trample over the Constitution
"Grandmother, what big ears you have!" - PRISM
"All the better to hear with, my child."
"Grandmother, what big eyes you have!" -- now the machine can analyze the CCTV better
"All the better to see with, my child."
"Grandmother, what big teeth you have got!" -- reach of the US government into foreign countries.
"All the better to eat you up with."

context (1)

roman_mir (125474) | about a year ago | (#44368051)

If you see a spoon on a picture, you can expect to see other objects commonly found in kitchens and restaurants or... there is no spoon.

Re:context (-1)

Anonymous Coward | about a year ago | (#44368109)

That post made as much sense as any of the other horse fecal matter you spew here.

Re: context (0)

Anonymous Coward | about a year ago | (#44368887)

The cake, however, ...

Re: context (0)

Anonymous Coward | about a year ago | (#44369845)

My spoon is too big.

20GB?? That's it??? (5, Funny)

Roshan Halappanavar (2994663) | about a year ago | (#44368055)

-"... using nothing but a single, multi-core machine with 20GB of RAM" Phew.. here i was thinking it'd need some unrealisticalll high specs from my PC!!

Re:20GB?? That's it??? (2)

technix4beos (471838) | about a year ago | (#44368077)

My current iMac has 32GB of RAM, so I don't see it as being too far fetched.

Re:20GB?? That's it??? (1)

Anonymous Coward | about a year ago | (#44368269)

did it cost an ARM to buy?

Re:20GB?? That's it??? (1)

Clsid (564627) | about a year ago | (#44368783)

Damn, I bought a MacBook last year and it had only 4 GB of RAM. I don't know what universe you guys live in, but it sure is greener on that side :)

Re:20GB?? That's it??? (1)

FatLittleMonkey (1341387) | about a year ago | (#44368999)

but it sure is greener on that side :)

Bluer. The future is luminescent blue.

(For about another 5 years. Then it will be the burnt orange vinyl of our generation.)

Re:20GB?? That's it??? (1)

ConceptJunkie (24823) | about a year ago | (#44370403)

The future will be orange and teal according to the movies. Then again, so is the present and the past.

Re:20GB?? That's it??? (0)

Anonymous Coward | about a year ago | (#44369099)

Given that every MacBook last year was available with 8 (Air) or 16gb (Pro) of RAM. You should have future proofed.

Re:20GB?? That's it??? (0)

Anonymous Coward | about a year ago | (#44370311)

Note the difference between iMac vs MacbookPro. One is a desktop machine, another a laptop. Last year a friend bought a mac for the lab and they were also considering either 32GB or 16GB ram. It's pretty much normal nowadays. And yes, I have a laptop and just as you I have 4GB and am fine transcoding videos and playing games.

Re:20GB?? That's it??? (1)

Anonymous Coward | about a year ago | (#44368091)

This isn't 2005, 32GB in a workstation costs peanuts nowadays. Come out from under your rock.

Re:20GB?? That's it??? (3, Insightful)

Anonymous Coward | about a year ago | (#44368117)

This isn't 2005, 32GB in a workstation costs peanuts nowadays. Come out from under your rock.

Cashews, maybe, but not peanuts.

Re:20GB?? That's it??? (1)

ConceptJunkie (24823) | about a year ago | (#44370429)

Yeah, and the unbroken ones... not the "cashew pieces" you can get for a lot cheaper. Still, I recall the excitement when RAM went under $100 a megabyte.

Re:20GB?? That's it??? (1)

gl4ss (559668) | about a year ago | (#44368129)

This isn't 2005, 32GB in a workstation costs peanuts nowadays. Come out from under your rock.

a workstation is hardly "even a mobile computer".

now to more important things, is this algo good enough for sorting trash?

Re:20GB?? That's it??? (2)

quadrox (1174915) | about a year ago | (#44368159)

My laptop came equipped with 8 GB RAM - I upgraded it two 32 GB after finding out just how cheap RAM has become nowadays. I must admit to rarely being able to come anywhere near filling this up, but that is a good thing in itself. I still have some ~200 megapixel panoramas I need to stitch with hugin, so maybe it will come in handy then.

Re:20GB?? That's it??? (1)

pmontra (738736) | about a year ago | (#44368439)

Not every laptop can be upgraded to 32 GB. I'm looking for one that can. What model is it?

Re:20GB?? That's it??? (1)

quadrox (1174915) | about a year ago | (#44368761)

Dell Precision M6700.

Re:20GB?? That's it??? (1)

Vintowin (1476905) | about a year ago | (#44369349)

Mine as well. Thinkpad W530. Came with 8 GB standard, upgraded to 32GB RAM.

Re:20GB?? That's it??? (1)

mcgrew (92797) | about a year ago | (#44368839)

I'd have to buy or build a new computer. Neither of the two old towers will take more than a gig, and I'm not going to add any to this notebook, too much of a PITA.

All the old computers do what I need them to so it'll be a while before that happens. I guess if I needed this functionality I'd have to spend a few hundred bucks.

Speaking of it doing what I need, I guess I should get back to work on that book (yep, that's why I haven't been here much lately).

Re:20GB?? That's it??? (1)

Anonymous Coward | about a year ago | (#44368339)

My rule of thumb for building a new PC since the 90s has always been: $100 CPU, $100 RAM, $100 HDD, plus incidentals = $400-500 depending on what you need.

RAM prices are up since I bought my 16GB for $80 this winter, but you can still build a very nice PC with 20GB of RAM for under $500.

Re:20GB?? That's it??? (0)

Anonymous Coward | about a year ago | (#44369945)

Yeah, if you ignore: Mainboard, ALL of cooling, PSU, case, and most importantly GPU! Which alone costs $400-500 for a "workstation" one.

Re: 20GB?? That's it??? (1)

Alioth (221270) | about a year ago | (#44368389)

My laptop has 16GB. More than 20GB is not unusual in a workstation today.

Re:20GB?? That's it??? (1)

lobiusmoop (305328) | about a year ago | (#44368417)

Iit's irrelevant, Google is all about cloud computing, all the gruntwork would be happening elsewhere on a heavily compressed/uploaded copy of your data, much like their speech recognition on even the latest smartphones.

Re:20GB?? That's it??? (1)

mcgrew (92797) | about a year ago | (#44368859)

Google is all about cloud computing

I guess I won't need to build a new PC after all, then, because Google and the NSA already get too much data from me, the creepy fucks. Considering some of the things I google for I'm probably on some list already.

Let me know when I can do this without "the cloud." I don't like not having control over my own data and processes.

Re:20GB?? That's it??? (0)

Anonymous Coward | about a year ago | (#44368457)

my PC has 32GB ram just because ram is cheap, 8GB is $40 so 20 GB is $100 not really that much money

Re:20GB?? That's it??? (1)

K. S. Kyosuke (729550) | about a year ago | (#44368499)

and even mobile computers

Apparently, the stuff that Google hands out to I/O attendees is really worth the money!

Re:20GB?? That's it??? (1)

Anonymous Coward | about a year ago | (#44368589)

My laptop has 8 cores and 16gb ram

My 11" netbook has 2 cores and 4gb ram

What are you using? An Abacus?

Re:20GB?? That's it??? (1)

hrvatska (790627) | about a year ago | (#44369047)

-"... using nothing but a single, multi-core machine with 20GB of RAM" Phew.. here i was thinking it'd need some unrealisticalll high specs from my PC!!

My Thinkpad W530 has 32GB of RAM. Maybe you need a new PC.

Re:20GB?? That's it??? (2)

140Mandak262Jamuna (970587) | about a year ago | (#44369243)

At work I have two machines 32 cores 256 GB (one linux, one windows) for regression testing, a 32 core 24 GB machine for development and a 16 core 16 GB machine for paperwork, like emails, Rally, presentations etc. The spec is actually on the low end for a professional. Heck, we order the most powerful graphics cards on headless workstations without display (to do massively parallel computations).

Re:20GB?? That's it??? (1)

Shortguy881 (2883333) | about a year ago | (#44370037)

Dell sells a computer with 32 GB of RAM starting at $2000 and Apple at $2400. Both are desktops, but once it reaches manufacturers like this its pretty common place. Apple even has a 64 GB version available.

As for mobile devices, the HTC one has 2 GB, so using Moore's Law, we are looking at another 15 - 20 years for hand helds to have 20 GB of RAM. That's depending on whether you like David House's 18 months assertion or the more accurate 2 year approach, but according to the International Technology Roadmap for Semiconductors, its every three years now, so we are looking at, tops, 30 years.

Coming to mobile? (1)

faffod (905810) | about a year ago | (#44368115)

"...might bring high power visual recognition to simple desktops and even mobile computers... computed in less than 20 seconds using nothing but a single, multi-core machine with 20GB of RAM."

Right... and by mobile computers you mean computers that I can lug from one desk to another.

Re:Coming to mobile? (5, Informative)

real-modo (1460457) | about a year ago | (#44368147)

Wait, your phone can decode video?!? In real time, playing the movies at normal speed? How many kilograms does it weigh, and how long is the power lead? How big is the mortgage on it? (/socraticmethod)

The computer innovation process broadly goes like this: first algorithm sort-of works but is incredibly inefficient - tweaks on this - a rethinking of the whole approach that leads to massive speed-ups - further refinement - implementation of the algorithm in hardware, where it becomes just another specialized processor - everybody profits!.

This article is about the third, or possibly fourth, phase of the process. If it it works out, phase 5 is straightforward. By itself, step 5 typically leads to two orders of magnitude increase in performance, three orders of magnitude decrease in power consumption, and two to four orders of magnitude decrease in cost.

Phases 6 and 7 happen if and when enough people find the provided service useful. (If technologies are no good, that's when only rich people have them. Successful technologies, everyone gets access to eventually.)

Re:Coming to mobile? (2)

real-modo (1460457) | about a year ago | (#44368153)

Argh! There is no phase seven. Buffer overflow error.

Re:Coming to mobile? (4, Funny)

91degrees (207121) | about a year ago | (#44368239)

Phase 7 is profits. You obviously assumed phase 6 was "???".

Re:Coming to mobile? (1)

cheesybagel (670288) | about a year ago | (#44369361)

Phase seven is going back to software again. i.e. the Wheel of Reincarnation [catb.org] .

Remember DSPs, memory, onboard in sound cards? LISP Machines? Ageia PhysX cards? etc, etc.

Re:Coming to mobile? (1)

eennaarbrak (1089393) | about a year ago | (#44368421)

If technologies are no good, that's when only rich people have them. Successful technologies, everyone gets access to eventually

That seems like question begging. The popularity of a technology defines its success, not the other way around.

Re:Coming to mobile? (1)

faffod (905810) | about a year ago | (#44369199)

I quoted the summary, and pointed out that it is ridiculous to expect that this tech will be coming to mobile anytime soon. I pointed out that the only "mobile" that I can see this working on is something that I would have to lug around. So to use your socratic method, Why are you asking if my phone can decode video in realtime and why where you asking about weight and power, when I specifically was saying that this is not anything close to a mobile configuration?

One day this tech will be able to run on mobile, that's just the nature of progress. But one day I will also have the power of today's super computer in my pocket. Today, and for the foreseeable future this tech requires high end desktop level computers. When we get that level of computational power in mobile it will be far enough in the future that trying to predict that this tech is specifically going to be used for image processing is ludicrous.

Re:Coming to mobile? (0)

Anonymous Coward | about a year ago | (#44369433)

No part of the 20GB requirement is 'high-end'. It just requires DDR3 memory in any given computer, which is available for both desktops and laptops. The former can easily have 64GB without an insane cost. The latter can have 32GB quite happily, for a low cost, and - most importantly - is a mobile platform.

Re:Coming to mobile? (2)

loufoque (1400831) | about a year ago | (#44369415)

Surely you realize the video decoding on phones is done with dedicated hardware.
You could do it on the CPU though, the latest models (Galaxy S4 and all) should be powerful enough.

Re:Coming to mobile? (2)

cnettel (836611) | about a year ago | (#44368769)

"...might bring high power visual recognition to simple desktops and even mobile computers... computed in less than 20 seconds using nothing but a single, multi-core machine with 20GB of RAM."

Right... and by mobile computers you mean computers that I can lug from one desk to another.

Like the MacBook Pro Retina with 16 GB? The point of their approach seems to be lots and lots of RAM to do table lookups. The memory subsystem in a normal laptop is plenty fast for that. Bandwidth would be more of a problem than total space in a cellphone. If we had a compelling case for loads of RAM in a smartphone, it would be possible to design one without going wildly beyond current power or cost envelopes. A few more years of Moore and things will be fine.

Re:Coming to mobile? (3, Insightful)

faffod (905810) | about a year ago | (#44369263)

Current mobile seems to cap out at 2MB of RAM. There is a reason for this - power consumption. RAM requires a continuous trickle of power to maintain state. An increase in RAM leads to a direct increase in power consumption. Mobile improvements are going to be focused on power consumption rather than raw power. Moore's law will be followed, but it will not result in something that is 2x more RAM, it will result in something that is 2x less power drain. Ok, I will grant you that it will probably be a mix - some increase in RAM, some increase in computation, but a significant increase in battery life.

To go from 2GB to 30GB following Moore's law would take 8 years. I contend that it will take longer than that because we won't see exact doubling of specs due to improvements in power. Either way, 10 years is far enough out that I think the summary claiming that this will come to mobile is far fetched for now.

Re:Coming to mobile? (1)

hermitdev (2792385) | about a year ago | (#44370601)

Current mobile seems to cap out at 2MB of RAM.

Surely you meant to say 2GB of RAM. My Galaxy S3 has 1GB of RAM. Hell, even my POS work-issued BlackBerry 9310 has 512MB.

Yeah, well (3, Funny)

Anonymous Coward | about a year ago | (#44368127)

my cat can spot a Dentabite bag from across the room in 20 milliseconds, does that mean my cat has 20TB of RAM?

Re:Yeah, well (2)

pspahn (1175617) | about a year ago | (#44368249)

And on the same note, a dog can predict where a ball is going to be when you bounce it off a wall, but that doesn't qualify it to go around processing physics simulations.

Can it find Waldo?... (1)

kimgkimg (957949) | about a year ago | (#44368135)

... or Sarah Connor for that matter?

Re:Can it find Waldo?... (2)

lxs (131946) | about a year ago | (#44368169)

No but it can spy on you day and night.

Re:Can it find Waldo?... (3, Funny)

pspahn (1175617) | about a year ago | (#44368259)

Some years ago, I had an idea for a tool that would, in a nutshell, identify a plant simply from a photo and some metadata (time of year, geolocation, etc). I know how it would work (and it would work), but I came to the conclusion that someone (ie. Google) would use the methods to develop a tool that would do the same thing but for human faces.

It was at that point I decided to leave that box closed.

Re:Can it find Waldo?... (3, Informative)

Anonymous Coward | about a year ago | (#44368291)

There are several non-too-creepy apps that can identify plant species by a smartphone-photo of a single leaf.

http://leafsnap.com/about/

They seem to request metadata directly via your phone's location and time-of-request (their server, not your phone, does the pattern-matching). Which is convenient, although it may place you at a time and place you may rather not be placed, for instance if burying pirate gold under a particular tree.

Re:Can it find Waldo?... (1)

AmiMoJo (196126) | about a year ago | (#44368969)

You should develop it. Google will do it eventually, and it would be better for all of us if we had the same tech to balance the power a little.

Re:Can it find Waldo?... (0)

Anonymous Coward | about a year ago | (#44368247)

It can't find Waldo because he is black.

Damn racist image recognition algorithms. It is Kinect all over again.

Re:Can it find Waldo?... (0)

Anonymous Coward | about a year ago | (#44368377)

Speculation: If you have a roommate named Sarah Connor, now is probably a good time to move out on your own.
(I'm sure anything made by Google knows how to use the phone book^W^W^W a search engine.)

Captcha's be gone? (2, Interesting)

Suhas (232056) | about a year ago | (#44368137)

So Captcha's will become even easier to crack? Great, the sooner we can get rid of them, the better. As it is they are getting impossible to read by humans, thanks to idiots who don't know how to design them.

Re:Captcha's be gone? (5, Funny)

Anonymous Coward | about a year ago | (#44368357)

So Captcha's will become even easier to crack? Great, the sooner we can get rid of them, the better. As it is they are getting impossible to read by humans, thanks to idiots who don't know how to design them.

But there's no need to get rid of them if we'll all have a handy browser plugin that can decode them for us at the press of a button!

Re:Captcha's be gone? (1)

Anonymous Coward | about a year ago | (#44368525)

There will be new type of captchas. I just love trying to prove to a computer i'm a human and failing.

Re:Captcha's be gone? (1)

Anonymous Coward | about a year ago | (#44369327)

There will be new type of captchas. I just love trying to prove to a computer i'm a human and failing.

You mean, like this? [xkcd.com]

Spatial Hashing (0, Flamebait)

Pino Grigio (2232472) | about a year ago | (#44368155)

Is this really a breakthrough? Hashing of invariant properties in images isn't new.

Re:Spatial Hashing (5, Informative)

Anonymous Coward | about a year ago | (#44368233)

Yes, it's a breakthrough. It won the best paper award at this year's Conference on Computer Vision and Pattern Recognition, a tier 1 computer vision conference.

Hashing invarient properties in images isn't new, but,

banded winner-take-all hashing of histograms-of-oriented-gradient part filters and then using matches across those bands to identify a test feature's nearest neighbors, while simultaneously computing an upper bound or exact dot products of those test features with their nearest learned features, for up to 100,000 objects with small amounts of memory, is new.

Re:Spatial Hashing (1)

Pino Grigio (2232472) | about a year ago | (#44368307)

When you say small amounts, you mean 32Gb.

Re: Spatial Hashing (1)

Anonymous Coward | about a year ago | (#44368397)

That's a small amount.

Seriously, what's with all the 1980s throwbacks on here today...

Re: Spatial Hashing (0)

Anonymous Coward | about a year ago | (#44368569)

what's with this one guy acting like everyone and their grandma has 32GB of memory on their home computer

Re: Spatial Hashing (1)

140Mandak262Jamuna (970587) | about a year ago | (#44369269)

Whats with people acting as though everyone and their grandma should do it in their personal computer for some new technology to be a phenomenal breakthrough? Does your grandma compute page rank of billions of pages of the net in her home computer?

Re:Spatial Hashing (0)

Anonymous Coward | about a year ago | (#44368577)

I bet he means "less than other known approaches" or "as little memory as the less memory-hungry alternatives" or perhaps "for the first time, as little memory as we can actually fit on a single computer". All of which makes sense in context.

Re:Spatial Hashing (1)

Kjella (173770) | about a year ago | (#44369407)

When you say small amounts, you mean 32Gb.

Which according to newegg can be had for $229, sure it's not pocket change but if you're thinking of say a computer vision program for a car... that's a tree, that's a house, that's a dog, there's a child running around. I would imagine it's a lot easier to collect sensor data than to make sense of it in real time, if you can rapidly identify points of interest like facial recognition in photo cameras on steroids you can put processing power - and potentially directional sensors - to good use. For example, you very closely look for clues whether a pedestrian walking down the street past a crossing is going to make use of it, so should an AI driver. Blunt use of raw processing power will only take you so far.

Re:Spatial Hashing (1)

daaxix (218354) | about a year ago | (#44370193)

But is it a breakthrough compared with the normal way to speed up a convolution, that is to compute it in Fourier space using a Fast Fourier Transform (FFT) or variants (DFT, DCT), etc.? I don't know the answer to this and would like a comparison as it is very relevant to my research work...

Re:Spatial Hashing (0)

loufoque (1400831) | about a year ago | (#44369443)

A paper written by Google is always considered more significant than real academic research, even if it ignores all prior art.
See MapReduce for example. What a grand innovation from Google.

SKYNET (0)

Anonymous Coward | about a year ago | (#44368215)

This algorithm definitely goes into the next release of drone firmware.

Re:SKYNET (0)

Anonymous Coward | about a year ago | (#44368603)

I want a /. plugin that allows me to filter (read: delete, kill) comments based in keywords regex style. The first keyword I'd go for would be /[sS][kK][yY][nN][eE][tT]/ for sure fo' sho'.

Re:SKYNET (0)

Anonymous Coward | about a year ago | (#44368931)

/skynet/i

FTFY.

Re:SKYNET (0)

Anonymous Coward | about a year ago | (#44369147)

But then you'll miss out when someone talks about a Proskynetarion!

Per object memory (2)

gshegosh (1587463) | about a year ago | (#44368797)

20GB per 100000 objects is 209kB per object. Don't know what resolution each image was, but I think 200kB is quite small.

Re:Per object memory (0)

Anonymous Coward | about a year ago | (#44369507)

I looked for the word simultaneous in the original article and didn't see it. I'm sure they meant that they ran 100000 20 second tests. (About 23 days)

Re:Per object memory (0)

Anonymous Coward | about a year ago | (#44370257)

.BMP

How times change (0)

Anonymous Coward | about a year ago | (#44368881)

There was a time, and not so very long ago, when I was always very keen to hear what interesting thing Google had just invented, and excited to see what they'd do with it. Now my initial reaction to everything they do is "great, how are they going to use this to mess with me"?

BMW already scans for highway signs. (1)

140Mandak262Jamuna (970587) | about a year ago | (#44369117)

BMW has a forward facing camera under the rear view mirror that scans for highway signs for posted speed limit and no-passing signs and displays them on the dash. I am not it is basic car or you have to buy some advanced tech package for it.

Nice (2)

nospam007 (722110) | about a year ago | (#44369135)

It would be nice if it could identify bird species (or other animals) preferably up to specific individual animals, like they do it with whales and penguins already.
I'd gladly pay money for such a program instead of getting only a free version, where I can check if aunt Mary with a drink in hand is in any photo in my collection.
We have already been waiting for years to get a program that can identify bird songs after shazaa came out, no luck yet, but hey, after all many towns have already a program that tells them: Somebody shot somebody with a .45, 0.23 miles in that direction, so there is still hope.

Re:Nice (1)

Metabolife (961249) | about a year ago | (#44370237)

Imagine identifying food! Imagine the Instagram photos!

CVPR (0)

Anonymous Coward | about a year ago | (#44369175)

I was actually on that CVPR.
Yes it did get the best paper award.
The only question it got during the oral presentation was
"So what exactly is your contribution with this paper?"
Seriously folks. It has been done before. They just did an efficient hashing and that's all.
It is always dubious when a gold sponsor of the conference gets the best paper award for a trivial research work

Tag, You're It (1)

seven of five (578993) | about a year ago | (#44369213)

You have been tagged at the ATM
You have been tagged at the laundromat
You have been tagged at the Quickie Mart
You have been tagged at work
You have been tagged at the gym
You have been tagged.

Everything tastes like Chicken. (1)

citizenr (871508) | about a year ago | (#44369281)

Its fast, but training set is random garbage from YT thumbnails and they have NO PROCESS to assess accuracy. All they can do is measure precision and its ~16% on average. What this means is their algorithm could very well just say FACE every single time and by shear coincidence every sixth image in dataset contains some face - tada, you just reached 16% precision.

link to full text (0)

Anonymous Coward | about a year ago | (#44369295)

The page link -links to just the technical supplement
(very brief)
Here is the full link from one of the author pages.

http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/40814.pdf [googleusercontent.com]

Also kudos to google for publishing it to the public, aaron schwartz would be proud.

I'll believe it when I see it... in the real world (1)

conquistadorst (2759585) | about a year ago | (#44369393)

Being a software engineer myself I understand the sense of excitement accomplishment after completing internal testing. But as with many projects, as soon as this leaves the controlled "lab testing" environment it's a whole different ball game. Until then it's still a white paper product and I'd suggest remaining cautiously optimistic...

Re:I'll believe it when I see it... in the real wo (1)

tlhIngan (30335) | about a year ago | (#44370667)

Being a software engineer myself I understand the sense of excitement accomplishment after completing internal testing. But as with many projects, as soon as this leaves the controlled "lab testing" environment it's a whole different ball game. Until then it's still a white paper product and I'd suggest remaining cautiously optimistic...

It probably has been well tested "in the real world" - check out Google Goggles sometime (which is available for Android and iOS).

In fact, this probably came out of the stuff that Goggles does - where you snap a photo and Goggles figures out what's in it. If you snap a QR code, it'll decode it, a barcode, it'll pop up a Google search for that product. Other items it'll attempt to either OCR it or perform object recognition. Basically it gives a list of things (snap a sign and it'll probably try to OCR it, offer you a translation, tell you what kinds of cars it sees, etc).

This does not rule out deep neural networks (1)

Wierdy1024 (902573) | about a year ago | (#44369531)

Bear in mind, this particular method is just a way to quickly do a large number of convolutions and get statistically fairly accurate results for the most activated convolution kernels.

This isn't incompatible with deep neural network models. This method can be combined with them and provide the same speedup there.

That's a lot of objects (1)

shadowrat (1069614) | about a year ago | (#44370251)

I'm sure it would take me more than a few minutes to identify that many objects.

However, how fast can it find Waldo?

Inane comment by article (1)

sacrilicious (316896) | about a year ago | (#44370699)

One of the cited articles says

What is clear is that it is never safe to write off an approach in AI.

... which is an example of a (sadly) standard over-generalization often used by writers to sound important in a closing paragraph. IF the approach used by Google was being "written off" by someone somewhere, what we have here is one example of someone being wrong about something. Claiming, as the article does, that it's therefor impossible to judge any AI technique as a dead end is unsupported and in no way warranted by Google's research in this case.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?